aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2013-07-07tile: use soft-fp for fma() and fmaf()Chris Metcalf
The sfp-machine.h is based on the gcc version, but extended with required new macros by comparison with other architectures and by investigating the hardware support for FP on tile.
2013-07-05Update x86 and x86_64 ulps on AMD FX-8350 with GCC 4.8.1.Jeroen Albers
2013-07-05[AArch64] Regenerate libm-test-ulpsMarcus Shawcroft
2013-07-04Fix lock elision help text in INSTALL and configureSiddhesh Poyarekar
2013-07-04Update powerpc-fpu ULPs.Adhemerval Zanella
2013-07-04Sync sys/ptrace with Linux 3.10Andreas Jaeger
2013-07-03Condition sysdeps/arm/include/bits/setjmp.h contents on _ISOMAC.Joseph Myers
2013-07-03Regenerate powerpc-nofpu ULPs.Joseph Myers
2013-07-03Add x86 init-arch to nptlH.J. Lu
2013-07-03Update i386 ULPs.Allan McRae
* sysdeps/i386/fpu/libm-test-ulps: Update.
2013-07-02Update sparc ULPs.David S. Miller
* sysdeps/sparc/fpu/libm-test-ulps: Update.
2013-07-03m68k: update libm test ULPsAndreas Schwab
2013-07-02Update x86_64 ULPs.Markus Trippelsdorf
2013-07-02Regenerate MIPS ulps.Joseph Myers
2013-07-02Regenerate ARM ulps.Joseph Myers
2013-07-02Regenerate x86 and x86_64 ulps.Joseph Myers
2013-07-02Make soft-float ARM use soft-fp fma/fmaf.Joseph Myers
2013-07-02alpha: Update libm-test-ulps from scratchRichard Henderson
2013-07-02Add lock elision to NEWS fileAndi Kleen
2013-07-02Add a configure option to enable lock elision and disable by defaultAndi Kleen
Can be enabled with --enable-lock-elision=yes at configure time.
2013-07-02Disable elision for any pthread_mutexattr_settype callAndi Kleen
PTHREAD_MUTEX_NORMAL requires deadlock for nesting, DEFAULT does not. Since glibc uses the same value (0) disable elision for any call to pthread_mutexattr_settype() with a 0 value. This implies that a program can disable elision by doing pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_NORMAL) Based on a original proposal by Rich Felker.
2013-07-02Add elision to pthread_mutex_{try,timed,un}lockAndi Kleen
Add elision paths to the basic mutex locks. The normal path has a check for RTM and upgrades the lock to RTM when available. Trylocks cannot automatically upgrade, so they check for elision every time. We use a 4 byte value in the mutex to store the lock elision adaptation state. This is separate from the adaptive spin state and uses a separate field. Condition variables currently do not support elision. Recursive mutexes and condition variables may be supported at some point, but are not in the current implementation. Also "trylock" will not automatically enable elision unless some other lock call has been already called on the lock. This version does not use IFUNC, so it means every lock has one additional check for elision. Benchmarking showed the overhead to be negligible.
2013-07-02Add minimal test suite changes for elision enabled kernelsAndi Kleen
tst-mutex5 and 8 test some behaviour not required by POSIX, that elision changes. This changes these tests to not check this when elision is enabled at configure time.
2013-07-02Add new internal mutex type flags for elision.Andi Kleen
Add Enable/disable flags used internally Extend the mutex initializers to have the fields needed for elision. The layout stays the same, and this is not visible to programs. These changes are not exposed outside pthread
2013-07-02Add the low level infrastructure for pthreads lock elision with TSXAndi Kleen
Lock elision using TSX is a technique to optimize lock scaling It allows to run locks in parallel using hardware support for a transactional execution mode in 4th generation Intel Core CPUs. See http://www.intel.com/software/tsx for more Information. This patch implements a simple adaptive lock elision algorithm based on RTM. It enables elision for the pthread mutexes and rwlocks. The algorithm keeps track whether a mutex successfully elides or not, and stops eliding for some time when it is not. When the CPU supports RTM the elision path is automatically tried, otherwise any elision is disabled. The adaptation algorithm and its tuning is currently preliminary. The code adds some checks to the lock fast paths. Micro-benchmarks show little to no difference without RTM. This patch implements the low level "lll_" code for lock elision. Followon patches hook this into the pthread implementation Changes with the RTM mutexes: ----------------------------- Lock elision in pthreads is generally compatible with existing programs. There are some obscure exceptions, which are expected to be uncommon. See the manual for more details. - A broken program that unlocks a free lock will crash. There are ways around this with some tradeoffs (more code in hot paths) I'm still undecided on what approach to take here; have to wait for testing reports. - pthread_mutex_destroy of a lock mutex will not return EBUSY but 0. - There's also a similar situation with trylock outside the mutex, "knowing" that the mutex must be held due to some other condition. In this case an assert failure cannot be recovered. This situation is usually an existing bug in the program. - Same applies to the rwlocks. Some of the return values changes (for example there is no EDEADLK for an elided lock, unless it aborts. However when elided it will also never deadlock of course) - Timing changes, so broken programs that make assumptions about specific timing may expose already existing latent problems. Note that these broken programs will break in other situations too (loaded system, new faster hardware, compiler optimizations etc.) - Programs with non recursive mutexes that take them recursively in a thread and which would always deadlock without elision may not always see a deadlock. The deadlock will only happen on an early or delayed abort (which typically happens at some point) This only happens for mutexes not explicitely set to PTHREAD_MUTEX_NORMAL or PTHREAD_MUTEX_ADAPTIVE_NP. PTHREAD_MUTEX_NORMAL mutexes do not elide. The elision default can be set at configure time. This patch implements the basic infrastructure for elision.
2013-07-02Enable static 32-bit SSE4.2 strcasecmp/strncasecmpH.J. Lu
2013-07-02Implement fma in soft-fp.Joseph Myers
2013-07-02ARM: Pass dl_hwcap to IFUNC resolver functions.Will Newton
2013-06-30Support no-FPU ColdFire in sysdeps/m68k/dl-trampoline.S and refactor code.Joseph Myers
2013-06-30tile: switch to using <fenv.h> fallback functionsChris Metcalf
Now that the fallback functions match the desired semantics for tile functions, just switch to using them.
2013-06-28Add more NEWS items for 2.18.Joseph Myers
2013-06-28Skip SSE4.2 versions on Intel SilvermontLiubov Dmitrieva
SSE2/SSSE3 versions are faster than SSE4.2 versions on Intel Silvermont.
2013-06-28PowerPC: Define AT_HWCAP2 bits and AT_HWCAP2 handling for POWER8.Ryan S. Arnold
2013-06-28Add GLRO(dl_hwcap2) for new AT_HWCAP2 auxv_t a_type.Ryan S. Arnold
2013-06-28Consistently use page_shift in sysdeps/unix/sysv/linux/mmap64.c.Joseph Myers
2013-06-28Test for mprotect failure in dl-load.c (bug 12492).Pierre Ynard
2013-06-28Mark packed structure element used with atomic operation aligned.Nathan Froyd
2013-06-28Fix sysdeps/m68k/fpu_control.h preprocessor indentation.Joseph Myers
2013-06-28Support no-FPU ColdFire in sysdeps/m68k/fpu_control.h.Nathan Sidwell
2013-06-28Add a dlopen/getpagesize static executable test.Maciej W. Rozycki
2013-06-28[BZ #15022] Correct global-scope dlopen issues in static executables.Maciej W. Rozycki
This change creates a link map in static executables to serve as the global search list for dlopen. It fixes a problem with the inability to access the global symbol object and a crash on an attempt to map a DSO into the global scope. Some code that has become dead after the addition of this link map is removed too and test cases are provided.
2013-06-28[AArch64] Adjust elf_machine_dynamic to find _DYNAMIC via _GLOBAL_OFFSET_TABLE_Marcus Shawcroft
2013-06-28[AArch64] Simplify getcontext pstate initialization.Marcus Shawcroft
2013-06-27_dl_static_init: Remove nested locking.Maciej W. Rozycki
This function is now called from dl_open_worker with the GL(dl_load_lock) lock held and no longer needs local protection. GL(dl_load_lock) also correctly protects _dl_lookup_symbol_x called here that relies on the caller to have serialized access to the data structures it uses.
2013-06-26Require GCC 4.4 or later to build glibc.Joseph Myers
2013-06-26Add a test for BZ #15674H.J. Lu
2013-06-26Mention BZ #15674H.J. Lu
2013-06-26Fix buffers overrun in x86_64 memcmp-ssse3.SLiubov Dmitrieva
2013-06-26[BZ #15022] Avoid repeated calls to DL_STATIC_INIT for the same module.Maciej W. Rozycki
2013-06-26Add AT_HWCAP2 as a new auxv_t a_type to elf.h.Ryan S. Arnold